What is it about?

It is quite common to see polarized opinions on the same issue. It is often much harder to see how exactly they differ, especially when one has to go over a large amount of information to figure it out. This study demonstrated a computational method that can help us to see more clearly which specific aspects may separate people's opinions. We analyzed more than 3,000 Amazon customer reviews of a controversial bestseller - The Da Vinci Code. The opinions were polarized with 1,738 positive ratings and 918 negative ones. The key question was: what led to the positive opinions and what led to the negative ones? We constructed a decision tree of highly predictive terms from both types of opinions to enable analysts to better understand the underlying differences. For example, whether one considered the book as a fiction or not can explain a great deal of the conflicting opinions. In this way, it becomes possible for us to pinpoint the reasons people disagree at a deeper level of granularity.

Featured Image

Why is it important?

In reality, it is certainly very useful to know how many people are in favor of a topic and how many people go for the opposite. It is, however, far more important for us to know why people differ in their opinions and their interpretations, which may also lead to more constructive debates and conversations that may even resolve the differences at a different level of granularity. This work demonstrates a visual analytic approach that can help us to reach a more reliable assessment of a situation and develop a more robust situation awareness.

Read the Original

This page is a summary of: Visual Analysis of Conflicting Opinions, October 2006, Institute of Electrical & Electronics Engineers (IEEE),
DOI: 10.1109/vast.2006.261431.
You can read the full text:

Read

Contributors

The following have contributed to this page